Challenge report Recognizing Families In the Wild Data Challenge

@article{Luo2020ChallengeRR,
  title={Challenge report Recognizing Families In the Wild Data Challenge},
  author={Zhipeng Luo and Zhiguang Zhang and Zhenyu Xu and Lixuan Che},
  journal={2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)},
  year={2020},
  pages={868-871}
}
  • Zhipeng Luo, Zhiguang Zhang, Lixuan Che
  • Published 30 May 2020
  • Computer Science
  • 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)
This paper is a brief report to our submission to the Recognizing Families In the Wild Data Challenge (4th Edition), in conjunction with FG 2020 Forum. Automatic kinship recognition has attracted many researchers' attention for its full application, but it is still a very challenging task because of the limited information that can be used to determine whether a pair of faces are blood relatives or not. In this paper, we studied previous methods and proposed our method. We try many methods… 

Tables from this paper

The 5th Recognizing Families in the Wild Data Challenge: Predicting Kinship from Faces
TLDR
Submissions for this year's RFIW are summarized, and the results for kinship verification, tri-subject verification, and family member search and retrieval are reviewed.
Recognizing Families In the Wild (RFIW): The 4th Edition
  • Joseph P. Robinson, Yu Yin, Y. Fu
  • Computer Science
    2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)
  • 2020
TLDR
The purpose of this paper is to describe the 2020 RFIW challenge, end-to-end, along with forecasts in promising future directions.
Visual Kinship Recognition: A Decade in the Making
TLDR
The public resources and data challenges that enabled and inspired many to hone-in on one or more views of automatic kinship recognition in the visual domain are reviewed and a stronghold for the state of progress is established for the different problems in a consistent manner.
Survey on the Analysis and Modeling of Visual Kinship: A Decade in the Making
TLDR
The public resources and data challenges that enabled and inspired many to hone-in on the views of automatic kinship recognition in the visual domain are reviewed and a stronghold for the state of progress for the different problems is established.
Patch-Based Dual-Tree Complex Wavelet Transform for Kinship Recognition
TLDR
Novel patch-based kinship recognition methods based on dual-tree complex wavelet transform (DT-CWT) and Selective Patch-Based DT-C WT are presented, which achieves competitive accuracy to state-of-the-art methods and representative patches contribute more similarities in parent/child image pairs and improve kinship accuracy.

References

SHOWING 1-10 OF 15 REFERENCES
Kinship Verification on Families in the Wild with Marginalized Denoising Metric Learning
TLDR
This work proposes a denoising auto-encoder based robust metric learning (DML) framework and its marginalized version (mD ML) to explicitly preserve the intrinsic structure of data and simultaneously endow the discriminative information into the learned features.
Families in the Wild (FIW): Large-Scale Kinship Image Database and Benchmarks
TLDR
This work presents the largest kinship recognition dataset to date, Families in the Wild, and demonstrates that a pre-trained Convolutional Neural Network as an off-the-shelf feature extractor outperforms the other feature types.
Recognizing Families In the Wild (RFIW): Data Challenge Workshop in conjunction with ACM MM 2017
TLDR
This manuscript uses this manuscript to summarize evaluation protocols, progress made and some technical background and performance ratings of the algorithms used, and a discussion on promising directions for both research and engineers to be taken next in this line of work.
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
TLDR
A benchmark task to recognize one million celebrities from their face images, by using all the possibly collected face images of this individual on the web as training data, which could lead to one of the largest classification problems in computer vision.
Visual Kinship Recognition of Families in the Wild
TLDR
It is shown that pre-trained CNN models fine-tuned on FIW outscores other conventional methods and achieved state-of-the art on the renowned KinWild datasets and is statistically compare FIW to related datasets, which unarguably shows enormous gains in overall size and amount of information encapsulated in the labels.
VGGFace2: A Dataset for Recognising Faces across Pose and Age
TLDR
A new large-scale face dataset named VGGFace2 is introduced, which contains 3.31 million images of 9131 subjects, with an average of 362.6 images for each subject, and the automated and manual filtering stages to ensure a high accuracy for the images of each identity are described.
FaceNet: A unified embedding for face recognition and clustering
TLDR
A system that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity, and achieves state-of-the-art face recognition performance using only 128-bytes perface.
Deep Residual Learning for Image Recognition
TLDR
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
Focal Loss for Dense Object Detection
TLDR
This paper proposes to address the extreme foreground-background class imbalance encountered during training of dense detectors by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples, and develops a novel Focal Loss, which focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.
In Defense of the Triplet Loss for Person Re-Identification
TLDR
It is shown that, for models trained from scratch as well as pretrained ones, using a variant of the triplet loss to perform end-to-end deep metric learning outperforms most other published methods by a large margin.
...
...